[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BNKFS7EY3K4SSCPJEER3NK":3,"skill-same:01M7BNKFS7EY3K4SSCPJEER3NK":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BNKFS7EY3K4SSCPJEER3NK","skilltta-task-guidance",null,"Temporary guidance for analyzing SEC 13F hedge fund filings across Q2\u002FQ3 2025 datasets, with emphasis on verifying helper-script paths before invocation.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Fsingle-sec-financial-report-RI-001\u002Frepaired_skill\u002Fskilltta-task-guidance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skilltta-task-guidance\ndescription: Temporary guidance for analyzing SEC 13F hedge fund filings across Q2\u002FQ3 2025 datasets, with emphasis on verifying helper-script paths before invocation.\n---\n\n# Task Guidance: 13F Hedge Fund Q2→Q3 Comparison\n\n## Context\nYou are comparing 13F filings between `\u002Froot\u002F2025-q2` and `\u002Froot\u002F2025-q3`. The data is typically a set of TSV\u002FSQLite tables (COVERPAGE, SUBMISSION, INFOTABLE, etc.). You must produce `\u002Froot\u002Fanswers.json`.\n\nTwo relevant skills exist in the environment:\n- `13f-analyzer\u002FSKILL.md`\n- `fuzzy-name-search\u002FSKILL.md`\n\n**The location hint explicitly flags that the helper-script invocation paths and path conventions in these two SKILL.md files may be wrong.** Do NOT trust the documented commands blindly.\n\n## Mandatory First Step: Verify Skill Paths\nBefore running any helper command from either skill:\n1. `ls` the skill directory (e.g. `ls -la \u003Cskills_root>\u002F13f-analyzer\u002F` and `...\u002Ffuzzy-name-search\u002F`) to see what scripts actually exist.\n2. Open `SKILL.md` and read the documented command, then compare with the real script filename and location.\n3. If the SKILL.md says e.g. `python scripts\u002Ffoo.py ...` but the file is at `.\u002Ffoo.py` or `bin\u002Ffoo.py`, adjust the invocation. Common fixes:\n   - Wrong relative directory (`scripts\u002F` vs root of skill)\n   - Wrong dataset path argument (needs absolute `\u002Froot\u002F2025-q2`, not a default)\n   - Needing to `cd` into the skill directory first, or conversely needing to run from `\u002Froot`.\n4. Patch the SKILL.md call site in your plan (do not necessarily edit the file; just use the corrected command).\n\n## Workflow Per Question\n\n### Q1 – Renaissance Technologies AUM (Q3)\n1. Use fuzzy-name-search skill on COVERPAGE in `\u002Froot\u002F2025-q3` with term `\"renaissance technologies\"`. Pick highest-score match → `accession_number`.\n2. Use 13f-analyzer to pull fund detail for that accession → extract AUM (likely sum of `VALUE` in INFOTABLE, or a reported AUM field; follow the skill's documented aggregation). Return as a number.\n\n### Q2 – Number of stocks held by Renaissance (Q3)\nUsing the same accession from Q1, count distinct holdings. Prefer counting rows in INFOTABLE for that accession (or distinct CUSIPs — read the skill's convention; typically it is row count of positions). Return integer.\n\n### Q3 – Berkshire Hathaway top-5 CUSIP increases Q2→Q3\n1. Fuzzy-search COVERPAGE in both `\u002Froot\u002F2025-q2` and `\u002Froot\u002F2025-q3` for `\"berkshire hathaway\"`. Keep the Buffett entity (Berkshire Hathaway Inc, Omaha) — disambiguate if multiple hits by picking the one with largest portfolio \u002F matching filer name.\n2. Load INFOTABLE holdings for each accession.\n3. Join on CUSIP; compute `delta_value = value_q3 - value_q2` (treat missing Q2 as 0 — these are new positions and count as increases).\n4. Sort descending by `delta_value`, take top 5 CUSIPs. Return as list in that order.\n\n### Q4 – Top-3 managers holding Palantir by share value in Q3\n1. Find Palantir's CUSIP. Approach: search INFOTABLE for issuer name containing `PALANTIR` across Q3 dataset and inspect the dominant CUSIP (Palantir Technologies Class A — commonly `69608A108`). Verify empirically from the data, do not hardcode.\n2. Filter all Q3 INFOTABLE rows with that CUSIP, group by accession_number, sum `VALUE`.\n3. Join with COVERPAGE\u002FSUBMISSION on accession_number to get filer\u002Fmanager NAME.\n4. Sort descending by summed value, take top 3 manager names. Return as list.\n\n## Output\nWrite exactly:\n```json\n{\n  \"q1_answer\": \u003Cnumber>,\n  \"q2_answer\": \u003Cnumber>,\n  \"q3_answer\": [\"...\",\"...\",\"...\",\"...\",\"...\"],\n  \"q4_answer\": [\"...\",\"...\",\"...\"]\n}\n```\nto `\u002Froot\u002Fanswers.json`. Numbers must be bare JSON numbers (not strings).\n\n## Patterns Borrowed From Reference Solutions\n- **SQLite + pandas** (ref: BigCodeBench\u002F408): if the 13F data is in SQLite, use\n  ```python\n  import sqlite3, pandas as pd\n  with sqlite3.connect(db_file) as conn:\n      df = pd.read_sql_query(query, conn)\n  ```\n  This is the cleanest way to run joins\u002Faggregations for Q3 and Q4.\n- **CSV\u002FTSV ingestion with explicit schema** (ref: BigCodeBench\u002F784): if data is TSV, read with `pd.read_csv(path, sep='\\t', dtype=str)` then coerce numeric columns (`VALUE`, `SSHPRNAMT`) with `pd.to_numeric(..., errors='coerce')` before summing.\n- **Robust file loading with existence checks** (ref: BigCodeBench\u002F381): before each step, assert the file\u002Fdir exists; drop NaN rows on key columns (CUSIP, VALUE) to avoid groupby surprises; wrap in try\u002Fexcept to surface the real error path, which is especially useful when the skill helper scripts have broken paths.\n\n## Defensive Tips\n- Dollar values in 13F are typically reported in thousands — be consistent across Q2 and Q3 (both will use same unit, so deltas are fine without unit conversion). For Q1 AUM, report in the same unit the 13f-analyzer skill returns; if ambiguous, prefer raw dollars (×1000).\n- When fuzzy matching, lowercase and strip punctuation. If the fuzzy-name-search script errors out, fall back to a direct SQL `LIKE '%RENAISSANCE%TECH%'` or pandas `str.contains` query on COVERPAGE.NAME.\n- Berkshire often has multiple filings per quarter (amendments). Prefer the latest\u002Flargest filing per quarter; if two accessions, pick the one whose INFOTABLE sum is largest (the primary 13F-HR).\n- Always print intermediate results (accession numbers, row counts, top-10 before truncating to top-5\u002F3) so a reviewer can audit the chain.\n","# Task Guidance: 13F Hedge Fund Q2→Q3 Comparison\n\n## Context\nYou are comparing 13F filings between `\u002Froot\u002F2025-q2` and `\u002Froot\u002F2025-q3`. The data is typically a set of TSV\u002FSQLite tables (COVERPAGE, SUBMISSION, INFOTABLE, etc.). You must produce `\u002Froot\u002Fanswers.json`.\n\nTwo relevant skills exist in the environment:\n- `13f-analyzer\u002FSKILL.md`\n- `fuzzy-name-search\u002FSKILL.md`\n\n**The location hint explicitly flags that the helper-script invocation paths and path conventions in these two SKILL.md files may be wrong.** Do NOT trust the documented commands blindly.\n\n## Mandatory First Step: Verify Skill Paths\nBefore running any helper command from either skill:\n1. `ls` the skill directory (e.g. `ls -la \u003Cskills_root>\u002F13f-analyzer\u002F` and `...\u002Ffuzzy-name-search\u002F`) to see what scripts actually exist.\n2. Open `SKILL.md` and read the documented command, then compare with the real script filename and location.\n3. If the SKILL.md says e.g. `python scripts\u002Ffoo.py ...` but the file is at `.\u002Ffoo.py` or `bin\u002Ffoo.py`, adjust the invocation. Common fixes:\n   - Wrong relative directory (`scripts\u002F` vs root of skill)\n   - Wrong dataset path argument (needs absolute `\u002Froot\u002F2025-q2`, not a default)\n   - Needing to `cd` into the skill directory first, or conversely needing to run from `\u002Froot`.\n4. Patch the SKILL.md call site in your plan (do not necessarily edit the file; just use the corrected command).\n\n## Workflow Per Question\n\n### Q1 – Renaissance Technologies AUM (Q3)\n1. Use fuzzy-name-search skill on COVERPAGE in `\u002Froot\u002F2025-q3` with term `\"renaissance technologies\"`. Pick highest-score match → `accession_number`.\n2. Use 13f-analyzer to pull fund detail for that accession → extract AUM (likely sum of `VALUE` in INFOTABLE, or a reported AUM field; follow the skill's documented aggregation). Return as a number.\n\n### Q2 – Number of stocks held by Renaissance (Q3)\nUsing the same accession from Q1, count distinct holdings. Prefer counting rows in INFOTABLE for that accession (or distinct CUSIPs — read the skill's convention; typically it is row count of positions). Return integer.\n\n### Q3 – Berkshire Hathaway top-5 CUSIP increases Q2→Q3\n1. Fuzzy-search COVERPAGE in both `\u002Froot\u002F2025-q2` and `\u002Froot\u002F2025-q3` for `\"berkshire hathaway\"`. Keep the Buffett entity (Berkshire Hathaway Inc, Omaha) — disambiguate if multiple hits by picking the one with largest portfolio \u002F matching filer name.\n2. Load INFOTABLE holdings for each accession.\n3. Join on CUSIP; compute `delta_value = value_q3 - value_q2` (treat missing Q2 as 0 — these are new positions and count as increases).\n4. Sort descending by `delta_value`, take top 5 CUSIPs. Return as list in that order.\n\n### Q4 – Top-3 managers holding Palantir by share value in Q3\n1. Find Palantir's CUSIP. Approach: search INFOTABLE for issuer name containing `PALANTIR` across Q3 dataset and inspect the dominant CUSIP (Palantir Technologies Class A — commonly `69608A108`). Verify empirically from the data, do not hardcode.\n2. Filter all Q3 INFOTABLE rows with that CUSIP, group by accession_number, sum `VALUE`.\n3. Join with COVERPAGE\u002FSUBMISSION on accession_number to get filer\u002Fmanager NAME.\n4. Sort descending by summed value, take top 3 manager names. Return as list.\n\n## Output\nWrite exactly:\n```json\n{\n  \"q1_answer\": \u003Cnumber>,\n  \"q2_answer\": \u003Cnumber>,\n  \"q3_answer\": [\"...\",\"...\",\"...\",\"...\",\"...\"],\n  \"q4_answer\": [\"...\",\"...\",\"...\"]\n}\n```\nto `\u002Froot\u002Fanswers.json`. Numbers must be bare JSON numbers (not strings).\n\n## Patterns Borrowed From Reference Solutions\n- **SQLite + pandas** (ref: BigCodeBench\u002F408): if the 13F data is in SQLite, use\n  ```python\n  import sqlite3, pandas as pd\n  with sqlite3.connect(db_file) as conn:\n      df = pd.read_sql_query(query, conn)\n  ```\n  This is the cleanest way to run joins\u002Faggregations for Q3 and Q4.\n- **CSV\u002FTSV ingestion with explicit schema** (ref: BigCodeBench\u002F784): if data is TSV, read with `pd.read_csv(path, sep='\\t', dtype=str)` then coerce numeric columns (`VALUE`, `SSHPRNAMT`) with `pd.to_numeric(..., errors='coerce')` before summing.\n- **Robust file loading with existence checks** (ref: BigCodeBench\u002F381): before each step, assert the file\u002Fdir exists; drop NaN rows on key columns (CUSIP, VALUE) to avoid groupby surprises; wrap in try\u002Fexcept to surface the real error path, which is especially useful when the skill helper scripts have broken paths.\n\n## Defensive Tips\n- Dollar values in 13F are typically reported in thousands — be consistent across Q2 and Q3 (both will use same unit, so deltas are fine without unit conversion). For Q1 AUM, report in the same unit the 13f-analyzer skill returns; if ambiguous, prefer raw dollars (×1000).\n- When fuzzy matching, lowercase and strip punctuation. If the fuzzy-name-search script errors out, fall back to a direct SQL `LIKE '%RENAISSANCE%TECH%'` or pandas `str.contains` query on COVERPAGE.NAME.\n- Berkshire often has multiple filings per quarter (amendments). Prefer the latest\u002Flargest filing per quarter; if two accessions, pick the one whose INFOTABLE sum is largest (the primary 13F-HR).\n- Always print intermediate results (accession numbers, row counts, top-10 before truncating to top-5\u002F3) so a reviewer can audit the chain.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","controlled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Fsingle-sec-financial-report-RI-001\u002Frepaired_skill\u002Fskilltta-task-guidance",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill skilltta-task-guidance",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill skilltta-task-guidance",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill skilltta-task-guidance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fskilltta-claude4.7\u002Ftasks\u002Fsingle-sec-financial-report-RI-001\u002Frepaired_skill\u002Fskilltta-task-guidance\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]